ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond.
Qiming ZhangYufei XuJing ZhangDacheng TaoPublished in: Int. J. Comput. Vis. (2023)
Keyphrases
- image recognition
- inductive bias
- inductive learning
- machine learning
- computer vision
- image processing
- pattern recognition
- face recognition
- pac learning
- prior knowledge
- domain knowledge
- supervised learning
- image classification
- domain theory
- image retrieval
- knowledge acquisition
- training examples
- machine learning algorithms
- pavement distress
- previously unseen
- multitask learning
- small number
- training set
- feature space
- decision trees
- learning algorithm